Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4471 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.1639. Min Range: -1.1639

Max Act: 1.1639. Min Act: -0.0003

Data Index: 62038 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 1.1639. Min Range: -1.1639

Max Act: 1.0577. Min Act: -0.0002

Data Index: 488101 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 1.1639. Min Range: -1.1639

Max Act: 1.0523. Min Act: -0.0002

Data Index: 485157 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 1.1639. Min Range: -1.1639

Max Act: 1.0269. Min Act: -0.0002

Data Index: 91954 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 1.1639. Min Range: -1.1639

Max Act: 1.0276. Min Act: -0.0002

Data Index: 553686 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 1.1639. Min Range: -1.1639

Max Act: 1.0227. Min Act: -0.0002

Data Index: 989025 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 1.1639. Min Range: -1.1639

Max Act: 1.0335. Min Act: -0.0002

Data Index: 503185 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 1.1639. Min Range: -1.1639

Max Act: 1.0247. Min Act: -0.0002

Data Index: 186227 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 1.1639. Min Range: -1.1639

Max Act: 1.0099. Min Act: -0.0002

Data Index: 1108356 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.1639. Min Range: -1.1639

Max Act: 1.0047. Min Act: -0.0002

Data Index: 258827 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.9838. Min Act: -0.0002

Data Index: 1041102 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.9962. Min Act: -0.0002

Data Index: 170457 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.9856. Min Act: -0.0002

Data Index: 1043092 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.9908. Min Act: -0.0002

Data Index: 730682 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.9734. Min Act: -0.0002

Data Index: 1081331 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.9652. Min Act: -0.0002

Data Index: 584791 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.9908. Min Act: -0.0002

Data Index: 1065850 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.9749. Min Act: -0.0002

Data Index: 173359 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.9629. Min Act: -0.0002

Data Index: 1233478 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 1.1639. Min Range: -1.1639

Max Act: 0.9534. Min Act: -0.0002

Data Index: 1310843 (C4 (Web Text))

Max Activating Token Index: 37